AVX512FP16: Add vcvttph2w/vcvttph2uw/vcvttph2dq/vcvttph2qq/vcvttph2udq/vcvttph2uqq
gcc/ChangeLog: * config/i386/avx512fp16intrin.h (_mm512_cvttph_epi32): New intrinsic. (_mm512_mask_cvttph_epi32): Likewise. (_mm512_maskz_cvttph_epi32): Likewise. (_mm512_cvtt_roundph_epi32): Likewise. (_mm512_mask_cvtt_roundph_epi32): Likewise. (_mm512_maskz_cvtt_roundph_epi32): Likewise. (_mm512_cvttph_epu32): Likewise. (_mm512_mask_cvttph_epu32): Likewise. (_mm512_maskz_cvttph_epu32): Likewise. (_mm512_cvtt_roundph_epu32): Likewise. (_mm512_mask_cvtt_roundph_epu32): Likewise. (_mm512_maskz_cvtt_roundph_epu32): Likewise. (_mm512_cvttph_epi64): Likewise. (_mm512_mask_cvttph_epi64): Likewise. (_mm512_maskz_cvttph_epi64): Likewise. (_mm512_cvtt_roundph_epi64): Likewise. (_mm512_mask_cvtt_roundph_epi64): Likewise. (_mm512_maskz_cvtt_roundph_epi64): Likewise. (_mm512_cvttph_epu64): Likewise. (_mm512_mask_cvttph_epu64): Likewise. (_mm512_maskz_cvttph_epu64): Likewise. (_mm512_cvtt_roundph_epu64): Likewise. (_mm512_mask_cvtt_roundph_epu64): Likewise. (_mm512_maskz_cvtt_roundph_epu64): Likewise. (_mm512_cvttph_epi16): Likewise. (_mm512_mask_cvttph_epi16): Likewise. (_mm512_maskz_cvttph_epi16): Likewise. (_mm512_cvtt_roundph_epi16): Likewise. (_mm512_mask_cvtt_roundph_epi16): Likewise. (_mm512_maskz_cvtt_roundph_epi16): Likewise. (_mm512_cvttph_epu16): Likewise. (_mm512_mask_cvttph_epu16): Likewise. (_mm512_maskz_cvttph_epu16): Likewise. (_mm512_cvtt_roundph_epu16): Likewise. (_mm512_mask_cvtt_roundph_epu16): Likewise. (_mm512_maskz_cvtt_roundph_epu16): Likewise. * config/i386/avx512fp16vlintrin.h (_mm_cvttph_epi32): New intirnsic. (_mm_mask_cvttph_epi32): Likewise. (_mm_maskz_cvttph_epi32): Likewise. (_mm256_cvttph_epi32): Likewise. (_mm256_mask_cvttph_epi32): Likewise. (_mm256_maskz_cvttph_epi32): Likewise. (_mm_cvttph_epu32): Likewise. (_mm_mask_cvttph_epu32): Likewise. (_mm_maskz_cvttph_epu32): Likewise. (_mm256_cvttph_epu32): Likewise. (_mm256_mask_cvttph_epu32): Likewise. (_mm256_maskz_cvttph_epu32): Likewise. (_mm_cvttph_epi64): Likewise. (_mm_mask_cvttph_epi64): Likewise. (_mm_maskz_cvttph_epi64): Likewise. (_mm256_cvttph_epi64): Likewise. (_mm256_mask_cvttph_epi64): Likewise. (_mm256_maskz_cvttph_epi64): Likewise. (_mm_cvttph_epu64): Likewise. (_mm_mask_cvttph_epu64): Likewise. (_mm_maskz_cvttph_epu64): Likewise. (_mm256_cvttph_epu64): Likewise. (_mm256_mask_cvttph_epu64): Likewise. (_mm256_maskz_cvttph_epu64): Likewise. (_mm_cvttph_epi16): Likewise. (_mm_mask_cvttph_epi16): Likewise. (_mm_maskz_cvttph_epi16): Likewise. (_mm256_cvttph_epi16): Likewise. (_mm256_mask_cvttph_epi16): Likewise. (_mm256_maskz_cvttph_epi16): Likewise. (_mm_cvttph_epu16): Likewise. (_mm_mask_cvttph_epu16): Likewise. (_mm_maskz_cvttph_epu16): Likewise. (_mm256_cvttph_epu16): Likewise. (_mm256_mask_cvttph_epu16): Likewise. (_mm256_maskz_cvttph_epu16): Likewise. * config/i386/i386-builtin.def: Add new builtins. * config/i386/sse.md (avx512fp16_fix<fixunssuffix>_trunc<mode>2<mask_name><round_saeonly_name>): New. (avx512fp16_fix<fixunssuffix>_trunc<mode>2<mask_name>): Ditto. (*avx512fp16_fix<fixunssuffix>_trunc<mode>2_load<mask_name>): Ditto. (avx512fp16_fix<fixunssuffix>_truncv2di2<mask_name>): Ditto. (avx512fp16_fix<fixunssuffix>_truncv2di2_load<mask_name>): Ditto. gcc/testsuite/ChangeLog: * gcc.target/i386/avx-1.c: Add test for new builtins. * gcc.target/i386/sse-13.c: Ditto. * gcc.target/i386/sse-23.c: Ditto. * gcc.target/i386/sse-14.c: Add test for new intrinsics. * gcc.target/i386/sse-22.c: Ditto.
This commit is contained in:
liuhongt
parent
babaa0e521
commit
c027accb42
|
|
@ -2702,6 +2702,203 @@ _mm512_maskz_cvt_roundph_epu32 (__mmask16 __A, __m256h __B, int __C)
|
|||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvttph2dq. */
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvttph_epi32 (__m256h __A)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2dq512_mask_round (__A,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask16) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvttph_epi32 (__m512i __A, __mmask16 __B, __m256h __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2dq512_mask_round (__C,
|
||||
(__v16si) __A,
|
||||
__B,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvttph_epi32 (__mmask16 __A, __m256h __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2dq512_mask_round (__B,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvtt_roundph_epi32 (__m256h __A, int __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2dq512_mask_round (__A,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask16) -1,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvtt_roundph_epi32 (__m512i __A, __mmask16 __B,
|
||||
__m256h __C, int __D)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2dq512_mask_round (__C,
|
||||
(__v16si) __A,
|
||||
__B,
|
||||
__D);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvtt_roundph_epi32 (__mmask16 __A, __m256h __B, int __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2dq512_mask_round (__B,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
__C);
|
||||
}
|
||||
|
||||
#else
|
||||
#define _mm512_cvtt_roundph_epi32(A, B) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2dq512_mask_round ((A), \
|
||||
(__v16si) \
|
||||
(_mm512_setzero_si512 ()), \
|
||||
(__mmask16)(-1), (B)))
|
||||
|
||||
#define _mm512_mask_cvtt_roundph_epi32(A, B, C, D) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2dq512_mask_round ((C), \
|
||||
(__v16si)(A), \
|
||||
(B), \
|
||||
(D)))
|
||||
|
||||
#define _mm512_maskz_cvtt_roundph_epi32(A, B, C) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2dq512_mask_round ((B), \
|
||||
(__v16si) \
|
||||
_mm512_setzero_si512 (), \
|
||||
(A), \
|
||||
(C)))
|
||||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvttph2udq. */
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvttph_epu32 (__m256h __A)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2udq512_mask_round (__A,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask16) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvttph_epu32 (__m512i __A, __mmask16 __B, __m256h __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2udq512_mask_round (__C,
|
||||
(__v16si) __A,
|
||||
__B,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvttph_epu32 (__mmask16 __A, __m256h __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2udq512_mask_round (__B,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvtt_roundph_epu32 (__m256h __A, int __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2udq512_mask_round (__A,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask16) -1,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvtt_roundph_epu32 (__m512i __A, __mmask16 __B,
|
||||
__m256h __C, int __D)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2udq512_mask_round (__C,
|
||||
(__v16si) __A,
|
||||
__B,
|
||||
__D);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvtt_roundph_epu32 (__mmask16 __A, __m256h __B, int __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2udq512_mask_round (__B,
|
||||
(__v16si)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
__C);
|
||||
}
|
||||
|
||||
#else
|
||||
#define _mm512_cvtt_roundph_epu32(A, B) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2udq512_mask_round ((A), \
|
||||
(__v16si) \
|
||||
_mm512_setzero_si512 (), \
|
||||
(__mmask16)-1, \
|
||||
(B)))
|
||||
|
||||
#define _mm512_mask_cvtt_roundph_epu32(A, B, C, D) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2udq512_mask_round ((C), \
|
||||
(__v16si)(A), \
|
||||
(B), \
|
||||
(D)))
|
||||
|
||||
#define _mm512_maskz_cvtt_roundph_epu32(A, B, C) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2udq512_mask_round ((B), \
|
||||
(__v16si) \
|
||||
_mm512_setzero_si512 (), \
|
||||
(A), \
|
||||
(C)))
|
||||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvtdq2ph. */
|
||||
extern __inline __m256h
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
|
|
@ -3019,6 +3216,156 @@ _mm512_maskz_cvt_roundph_epu64 (__mmask8 __A, __m128h __B, int __C)
|
|||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvttph2qq. */
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvttph_epi64 (__m128h __A)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq512_mask_round (__A,
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask8) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvttph_epi64 (__m512i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq512_mask_round (__C, __A, __B,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvttph_epi64 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq512_mask_round (__B,
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvtt_roundph_epi64 (__m128h __A, int __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq512_mask_round (__A,
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask8) -1,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvtt_roundph_epi64 (__m512i __A, __mmask8 __B, __m128h __C, int __D)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq512_mask_round (__C, __A, __B, __D);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvtt_roundph_epi64 (__mmask8 __A, __m128h __B, int __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq512_mask_round (__B,
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
__C);
|
||||
}
|
||||
|
||||
#else
|
||||
#define _mm512_cvtt_roundph_epi64(A, B) \
|
||||
(__builtin_ia32_vcvttph2qq512_mask_round ((A), \
|
||||
_mm512_setzero_si512 (), \
|
||||
(__mmask8)-1, \
|
||||
(B)))
|
||||
|
||||
#define _mm512_mask_cvtt_roundph_epi64(A, B, C, D) \
|
||||
__builtin_ia32_vcvttph2qq512_mask_round ((C), (A), (B), (D))
|
||||
|
||||
#define _mm512_maskz_cvtt_roundph_epi64(A, B, C) \
|
||||
(__builtin_ia32_vcvttph2qq512_mask_round ((B), \
|
||||
_mm512_setzero_si512 (), \
|
||||
(A), \
|
||||
(C)))
|
||||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvttph2uqq. */
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvttph_epu64 (__m128h __A)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq512_mask_round (__A,
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask8) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvttph_epu64 (__m512i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq512_mask_round (__C, __A, __B,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvttph_epu64 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq512_mask_round (__B,
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvtt_roundph_epu64 (__m128h __A, int __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq512_mask_round (__A,
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask8) -1,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvtt_roundph_epu64 (__m512i __A, __mmask8 __B, __m128h __C, int __D)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq512_mask_round (__C, __A, __B, __D);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvtt_roundph_epu64 (__mmask8 __A, __m128h __B, int __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq512_mask_round (__B,
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
__C);
|
||||
}
|
||||
|
||||
#else
|
||||
#define _mm512_cvtt_roundph_epu64(A, B) \
|
||||
(__builtin_ia32_vcvttph2uqq512_mask_round ((A), \
|
||||
_mm512_setzero_si512 (), \
|
||||
(__mmask8)-1, \
|
||||
(B)))
|
||||
|
||||
#define _mm512_mask_cvtt_roundph_epu64(A, B, C, D) \
|
||||
__builtin_ia32_vcvttph2uqq512_mask_round ((C), (A), (B), (D))
|
||||
|
||||
#define _mm512_maskz_cvtt_roundph_epu64(A, B, C) \
|
||||
(__builtin_ia32_vcvttph2uqq512_mask_round ((B), \
|
||||
_mm512_setzero_si512 (), \
|
||||
(A), \
|
||||
(C)))
|
||||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvtqq2ph. */
|
||||
extern __inline __m128h
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
|
|
@ -3363,6 +3710,204 @@ _mm512_maskz_cvt_roundph_epu16 (__mmask32 __A, __m512h __B, int __C)
|
|||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvttph2w. */
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvttph_epi16 (__m512h __A)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2w512_mask_round (__A,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask32) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvttph_epi16 (__m512i __A, __mmask32 __B, __m512h __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2w512_mask_round (__C,
|
||||
(__v32hi) __A,
|
||||
__B,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvttph_epi16 (__mmask32 __A, __m512h __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2w512_mask_round (__B,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvtt_roundph_epi16 (__m512h __A, int __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2w512_mask_round (__A,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask32) -1,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvtt_roundph_epi16 (__m512i __A, __mmask32 __B,
|
||||
__m512h __C, int __D)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2w512_mask_round (__C,
|
||||
(__v32hi) __A,
|
||||
__B,
|
||||
__D);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvtt_roundph_epi16 (__mmask32 __A, __m512h __B, int __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2w512_mask_round (__B,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
__C);
|
||||
}
|
||||
|
||||
#else
|
||||
#define _mm512_cvtt_roundph_epi16(A, B) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2w512_mask_round ((A), \
|
||||
(__v32hi) \
|
||||
_mm512_setzero_si512 (), \
|
||||
(__mmask32)-1, \
|
||||
(B)))
|
||||
|
||||
#define _mm512_mask_cvtt_roundph_epi16(A, B, C, D) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2w512_mask_round ((C), \
|
||||
(__v32hi)(A), \
|
||||
(B), \
|
||||
(D)))
|
||||
|
||||
#define _mm512_maskz_cvtt_roundph_epi16(A, B, C) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2w512_mask_round ((B), \
|
||||
(__v32hi) \
|
||||
_mm512_setzero_si512 (), \
|
||||
(A), \
|
||||
(C)))
|
||||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvttph2uw. */
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvttph_epu16 (__m512h __A)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2uw512_mask_round (__A,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask32) -1,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvttph_epu16 (__m512i __A, __mmask32 __B, __m512h __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2uw512_mask_round (__C,
|
||||
(__v32hi) __A,
|
||||
__B,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvttph_epu16 (__mmask32 __A, __m512h __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2uw512_mask_round (__B,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
_MM_FROUND_CUR_DIRECTION);
|
||||
}
|
||||
|
||||
#ifdef __OPTIMIZE__
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_cvtt_roundph_epu16 (__m512h __A, int __B)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2uw512_mask_round (__A,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
(__mmask32) -1,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_mask_cvtt_roundph_epu16 (__m512i __A, __mmask32 __B,
|
||||
__m512h __C, int __D)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2uw512_mask_round (__C,
|
||||
(__v32hi) __A,
|
||||
__B,
|
||||
__D);
|
||||
}
|
||||
|
||||
extern __inline __m512i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm512_maskz_cvtt_roundph_epu16 (__mmask32 __A, __m512h __B, int __C)
|
||||
{
|
||||
return (__m512i)
|
||||
__builtin_ia32_vcvttph2uw512_mask_round (__B,
|
||||
(__v32hi)
|
||||
_mm512_setzero_si512 (),
|
||||
__A,
|
||||
__C);
|
||||
}
|
||||
|
||||
#else
|
||||
#define _mm512_cvtt_roundph_epu16(A, B) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2uw512_mask_round ((A), \
|
||||
(__v32hi) \
|
||||
_mm512_setzero_si512 (), \
|
||||
(__mmask32)-1, \
|
||||
(B)))
|
||||
|
||||
#define _mm512_mask_cvtt_roundph_epu16(A, B, C, D) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2uw512_mask_round ((C), \
|
||||
(__v32hi)(A), \
|
||||
(B), \
|
||||
(D)))
|
||||
|
||||
#define _mm512_maskz_cvtt_roundph_epu16(A, B, C) \
|
||||
((__m512i) \
|
||||
__builtin_ia32_vcvttph2uw512_mask_round ((B), \
|
||||
(__v32hi) \
|
||||
_mm512_setzero_si512 (), \
|
||||
(A), \
|
||||
(C)))
|
||||
|
||||
#endif /* __OPTIMIZE__ */
|
||||
|
||||
/* Intrinsics vcvtw2ph. */
|
||||
extern __inline __m512h
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
|
|
|
|||
|
|
@ -1050,6 +1050,132 @@ _mm256_maskz_cvtph_epu32 (__mmask8 __A, __m128h __B)
|
|||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvttph2dq. */
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_cvttph_epi32 (__m128h __A)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2dq128_mask (__A,
|
||||
(__v4si) _mm_setzero_si128 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_cvttph_epi32 (__m128i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return (__m128i)__builtin_ia32_vcvttph2dq128_mask (__C,
|
||||
( __v4si) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_cvttph_epi32 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2dq128_mask (__B,
|
||||
(__v4si) _mm_setzero_si128 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_cvttph_epi32 (__m128h __A)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2dq256_mask (__A,
|
||||
(__v8si)
|
||||
_mm256_setzero_si256 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_mask_cvttph_epi32 (__m256i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2dq256_mask (__C,
|
||||
( __v8si) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maskz_cvttph_epi32 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2dq256_mask (__B,
|
||||
(__v8si)
|
||||
_mm256_setzero_si256 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvttph2udq. */
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_cvttph_epu32 (__m128h __A)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2udq128_mask (__A,
|
||||
(__v4si)
|
||||
_mm_setzero_si128 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_cvttph_epu32 (__m128i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2udq128_mask (__C,
|
||||
( __v4si) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_cvttph_epu32 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2udq128_mask (__B,
|
||||
(__v4si)
|
||||
_mm_setzero_si128 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_cvttph_epu32 (__m128h __A)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2udq256_mask (__A,
|
||||
(__v8si)
|
||||
_mm256_setzero_si256 (), (__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_mask_cvttph_epu32 (__m256i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2udq256_mask (__C,
|
||||
( __v8si) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maskz_cvttph_epu32 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2udq256_mask (__B,
|
||||
(__v8si)
|
||||
_mm256_setzero_si256 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvtdq2ph. */
|
||||
extern __inline __m128h
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
|
|
@ -1257,6 +1383,116 @@ _mm256_maskz_cvtph_epu64 (__mmask8 __A, __m128h __B)
|
|||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvttph2qq. */
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_cvttph_epi64 (__m128h __A)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq128_mask (__A,
|
||||
_mm_setzero_si128 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_cvttph_epi64 (__m128i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq128_mask (__C,
|
||||
__A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_cvttph_epi64 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq128_mask (__B,
|
||||
_mm_setzero_si128 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_cvttph_epi64 (__m128h __A)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq256_mask (__A,
|
||||
_mm256_setzero_si256 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_mask_cvttph_epi64 (__m256i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq256_mask (__C,
|
||||
__A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maskz_cvttph_epi64 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2qq256_mask (__B,
|
||||
_mm256_setzero_si256 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvttph2uqq. */
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_cvttph_epu64 (__m128h __A)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq128_mask (__A,
|
||||
_mm_setzero_si128 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_cvttph_epu64 (__m128i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq128_mask (__C,
|
||||
__A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_cvttph_epu64 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq128_mask (__B,
|
||||
_mm_setzero_si128 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_cvttph_epu64 (__m128h __A)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq256_mask (__A,
|
||||
_mm256_setzero_si256 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_mask_cvttph_epu64 (__m256i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq256_mask (__C,
|
||||
__A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maskz_cvttph_epu64 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return __builtin_ia32_vcvttph2uqq256_mask (__B,
|
||||
_mm256_setzero_si256 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvtqq2ph. */
|
||||
extern __inline __m128h
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
|
|
@ -1481,6 +1717,135 @@ _mm256_maskz_cvtph_epu16 (__mmask16 __A, __m256h __B)
|
|||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvttph2w. */
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_cvttph_epi16 (__m128h __A)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2w128_mask (__A,
|
||||
(__v8hi)
|
||||
_mm_setzero_si128 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_cvttph_epi16 (__m128i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2w128_mask (__C,
|
||||
( __v8hi) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_cvttph_epi16 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2w128_mask (__B,
|
||||
(__v8hi)
|
||||
_mm_setzero_si128 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_cvttph_epi16 (__m256h __A)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2w256_mask (__A,
|
||||
(__v16hi)
|
||||
_mm256_setzero_si256 (),
|
||||
(__mmask16) -1);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_mask_cvttph_epi16 (__m256i __A, __mmask16 __B, __m256h __C)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2w256_mask (__C,
|
||||
( __v16hi) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maskz_cvttph_epi16 (__mmask16 __A, __m256h __B)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2w256_mask (__B,
|
||||
(__v16hi)
|
||||
_mm256_setzero_si256 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvttph2uw. */
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_cvttph_epu16 (__m128h __A)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2uw128_mask (__A,
|
||||
(__v8hi)
|
||||
_mm_setzero_si128 (),
|
||||
(__mmask8) -1);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_mask_cvttph_epu16 (__m128i __A, __mmask8 __B, __m128h __C)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2uw128_mask (__C,
|
||||
( __v8hi) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m128i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm_maskz_cvttph_epu16 (__mmask8 __A, __m128h __B)
|
||||
{
|
||||
return (__m128i)
|
||||
__builtin_ia32_vcvttph2uw128_mask (__B,
|
||||
(__v8hi)
|
||||
_mm_setzero_si128 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_cvttph_epu16 (__m256h __A)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2uw256_mask (__A,
|
||||
(__v16hi)
|
||||
_mm256_setzero_si256 (),
|
||||
(__mmask16) -1);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_mask_cvttph_epu16 (__m256i __A, __mmask16 __B, __m256h __C)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2uw256_mask (__C,
|
||||
( __v16hi) __A,
|
||||
__B);
|
||||
}
|
||||
|
||||
extern __inline __m256i
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
_mm256_maskz_cvttph_epu16 (__mmask16 __A, __m256h __B)
|
||||
{
|
||||
return (__m256i)
|
||||
__builtin_ia32_vcvttph2uw256_mask (__B,
|
||||
(__v16hi) _mm256_setzero_si256 (),
|
||||
__A);
|
||||
}
|
||||
|
||||
/* Intrinsics vcvtw2ph. */
|
||||
extern __inline __m128h
|
||||
__attribute__ ((__gnu_inline__, __always_inline__, __artificial__))
|
||||
|
|
|
|||
|
|
@ -2835,14 +2835,26 @@ BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp1
|
|||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2dq_v8si_mask, "__builtin_ia32_vcvtph2dq256_mask", IX86_BUILTIN_VCVTPH2DQ256_MASK, UNKNOWN, (int) V8SI_FTYPE_V8HF_V8SI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2udq_v4si_mask, "__builtin_ia32_vcvtph2udq128_mask", IX86_BUILTIN_VCVTPH2UDQ128_MASK, UNKNOWN, (int) V4SI_FTYPE_V8HF_V4SI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2udq_v8si_mask, "__builtin_ia32_vcvtph2udq256_mask", IX86_BUILTIN_VCVTPH2UDQ256_MASK, UNKNOWN, (int) V8SI_FTYPE_V8HF_V8SI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv4si2_mask, "__builtin_ia32_vcvttph2dq128_mask", IX86_BUILTIN_VCVTTPH2DQ128_MASK, UNKNOWN, (int) V4SI_FTYPE_V8HF_V4SI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv8si2_mask, "__builtin_ia32_vcvttph2dq256_mask", IX86_BUILTIN_VCVTTPH2DQ256_MASK, UNKNOWN, (int) V8SI_FTYPE_V8HF_V8SI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv4si2_mask, "__builtin_ia32_vcvttph2udq128_mask", IX86_BUILTIN_VCVTTPH2UDQ128_MASK, UNKNOWN, (int) V4SI_FTYPE_V8HF_V4SI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv8si2_mask, "__builtin_ia32_vcvttph2udq256_mask", IX86_BUILTIN_VCVTTPH2UDQ256_MASK, UNKNOWN, (int) V8SI_FTYPE_V8HF_V8SI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2qq_v2di_mask, "__builtin_ia32_vcvtph2qq128_mask", IX86_BUILTIN_VCVTPH2QQ128_MASK, UNKNOWN, (int) V2DI_FTYPE_V8HF_V2DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2qq_v4di_mask, "__builtin_ia32_vcvtph2qq256_mask", IX86_BUILTIN_VCVTPH2QQ256_MASK, UNKNOWN, (int) V4DI_FTYPE_V8HF_V4DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2uqq_v2di_mask, "__builtin_ia32_vcvtph2uqq128_mask", IX86_BUILTIN_VCVTPH2UQQ128_MASK, UNKNOWN, (int) V2DI_FTYPE_V8HF_V2DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2uqq_v4di_mask, "__builtin_ia32_vcvtph2uqq256_mask", IX86_BUILTIN_VCVTPH2UQQ256_MASK, UNKNOWN, (int) V4DI_FTYPE_V8HF_V4DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv2di2_mask, "__builtin_ia32_vcvttph2qq128_mask", IX86_BUILTIN_VCVTTPH2QQ128_MASK, UNKNOWN, (int) V2DI_FTYPE_V8HF_V2DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv4di2_mask, "__builtin_ia32_vcvttph2qq256_mask", IX86_BUILTIN_VCVTTPH2QQ256_MASK, UNKNOWN, (int) V4DI_FTYPE_V8HF_V4DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv2di2_mask, "__builtin_ia32_vcvttph2uqq128_mask", IX86_BUILTIN_VCVTTPH2UQQ128_MASK, UNKNOWN, (int) V2DI_FTYPE_V8HF_V2DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv4di2_mask, "__builtin_ia32_vcvttph2uqq256_mask", IX86_BUILTIN_VCVTTPH2UQQ256_MASK, UNKNOWN, (int) V4DI_FTYPE_V8HF_V4DI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2w_v8hi_mask, "__builtin_ia32_vcvtph2w128_mask", IX86_BUILTIN_VCVTPH2W128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2w_v16hi_mask, "__builtin_ia32_vcvtph2w256_mask", IX86_BUILTIN_VCVTPH2W256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2uw_v8hi_mask, "__builtin_ia32_vcvtph2uw128_mask", IX86_BUILTIN_VCVTPH2UW128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2uw_v16hi_mask, "__builtin_ia32_vcvtph2uw256_mask", IX86_BUILTIN_VCVTPH2UW256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv8hi2_mask, "__builtin_ia32_vcvttph2w128_mask", IX86_BUILTIN_VCVTTPH2W128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv16hi2_mask, "__builtin_ia32_vcvttph2w256_mask", IX86_BUILTIN_VCVTTPH2W256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv8hi2_mask, "__builtin_ia32_vcvttph2uw128_mask", IX86_BUILTIN_VCVTTPH2UW128_MASK, UNKNOWN, (int) V8HI_FTYPE_V8HF_V8HI_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv16hi2_mask, "__builtin_ia32_vcvttph2uw256_mask", IX86_BUILTIN_VCVTTPH2UW256_MASK, UNKNOWN, (int) V16HI_FTYPE_V16HF_V16HI_UHI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtw2ph_v8hi_mask, "__builtin_ia32_vcvtw2ph128_mask", IX86_BUILTIN_VCVTW2PH128_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HI_V8HF_UQI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtw2ph_v16hi_mask, "__builtin_ia32_vcvtw2ph256_mask", IX86_BUILTIN_VCVTW2PH256_MASK, UNKNOWN, (int) V16HF_FTYPE_V16HI_V16HF_UHI)
|
||||
BDESC (OPTION_MASK_ISA_AVX512VL, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtuw2ph_v8hi_mask, "__builtin_ia32_vcvtuw2ph128_mask", IX86_BUILTIN_VCVTUW2PH128_MASK, UNKNOWN, (int) V8HF_FTYPE_V8HI_V8HF_UQI)
|
||||
|
|
@ -3084,10 +3096,16 @@ BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512bw_getmantv32hf_mask_round
|
|||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512f_vgetmantv8hf_mask_round, "__builtin_ia32_getmantsh_mask_round", IX86_BUILTIN_GETMANTSH_MASK_ROUND, UNKNOWN, (int) V8HF_FTYPE_V8HF_V8HF_INT_V8HF_UQI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2dq_v16si_mask_round, "__builtin_ia32_vcvtph2dq512_mask_round", IX86_BUILTIN_VCVTPH2DQ512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16HF_V16SI_UHI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2udq_v16si_mask_round, "__builtin_ia32_vcvtph2udq512_mask_round", IX86_BUILTIN_VCVTPH2UDQ512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16HF_V16SI_UHI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv16si2_mask_round, "__builtin_ia32_vcvttph2dq512_mask_round", IX86_BUILTIN_VCVTTPH2DQ512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16HF_V16SI_UHI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv16si2_mask_round, "__builtin_ia32_vcvttph2udq512_mask_round", IX86_BUILTIN_VCVTTPH2UDQ512_MASK_ROUND, UNKNOWN, (int) V16SI_FTYPE_V16HF_V16SI_UHI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2qq_v8di_mask_round, "__builtin_ia32_vcvtph2qq512_mask_round", IX86_BUILTIN_VCVTPH2QQ512_MASK_ROUND, UNKNOWN, (int) V8DI_FTYPE_V8HF_V8DI_UQI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2uqq_v8di_mask_round, "__builtin_ia32_vcvtph2uqq512_mask_round", IX86_BUILTIN_VCVTPH2UQQ512_MASK_ROUND, UNKNOWN, (int) V8DI_FTYPE_V8HF_V8DI_UQI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv8di2_mask_round, "__builtin_ia32_vcvttph2qq512_mask_round", IX86_BUILTIN_VCVTTPH2QQ512_MASK_ROUND, UNKNOWN, (int) V8DI_FTYPE_V8HF_V8DI_UQI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv8di2_mask_round, "__builtin_ia32_vcvttph2uqq512_mask_round", IX86_BUILTIN_VCVTTPH2UQQ512_MASK_ROUND, UNKNOWN, (int) V8DI_FTYPE_V8HF_V8DI_UQI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2w_v32hi_mask_round, "__builtin_ia32_vcvtph2w512_mask_round", IX86_BUILTIN_VCVTPH2W512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtph2uw_v32hi_mask_round, "__builtin_ia32_vcvtph2uw512_mask_round", IX86_BUILTIN_VCVTPH2UW512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fix_truncv32hi2_mask_round, "__builtin_ia32_vcvttph2w512_mask_round", IX86_BUILTIN_VCVTTPH2W512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_fixuns_truncv32hi2_mask_round, "__builtin_ia32_vcvttph2uw512_mask_round", IX86_BUILTIN_VCVTTPH2UW512_MASK_ROUND, UNKNOWN, (int) V32HI_FTYPE_V32HF_V32HI_USI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtw2ph_v32hi_mask_round, "__builtin_ia32_vcvtw2ph512_mask_round", IX86_BUILTIN_VCVTW2PH512_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HI_V32HF_USI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtuw2ph_v32hi_mask_round, "__builtin_ia32_vcvtuw2ph512_mask_round", IX86_BUILTIN_VCVTUW2PH512_MASK_ROUND, UNKNOWN, (int) V32HF_FTYPE_V32HI_V32HF_USI_INT)
|
||||
BDESC (0, OPTION_MASK_ISA2_AVX512FP16, CODE_FOR_avx512fp16_vcvtdq2ph_v16si_mask_round, "__builtin_ia32_vcvtdq2ph512_mask_round", IX86_BUILTIN_VCVTDQ2PH512_MASK_ROUND, UNKNOWN, (int) V16HF_FTYPE_V16SI_V16HF_UHI_INT)
|
||||
|
|
|
|||
|
|
@ -5934,6 +5934,60 @@
|
|||
(set_attr "prefix" "evex")
|
||||
(set_attr "mode" "HF")])
|
||||
|
||||
(define_insn "avx512fp16_fix<fixunssuffix>_trunc<mode>2<mask_name><round_saeonly_name>"
|
||||
[(set (match_operand:VI2H_AVX512VL 0 "register_operand" "=v")
|
||||
(any_fix:VI2H_AVX512VL
|
||||
(match_operand:<ssePHmode> 1 "<round_saeonly_nimm_predicate>" "<round_saeonly_constraint>")))]
|
||||
"TARGET_AVX512FP16"
|
||||
"vcvttph2<fixsuffix><sseintconvert>\t{<round_saeonly_mask_op2>%1, %0<mask_operand2>|%0<mask_operand2>, %1<round_saeonly_mask_op2>}"
|
||||
[(set_attr "type" "ssecvt")
|
||||
(set_attr "prefix" "evex")
|
||||
(set_attr "mode" "<sseinsnmode>")])
|
||||
|
||||
(define_insn "avx512fp16_fix<fixunssuffix>_trunc<mode>2<mask_name>"
|
||||
[(set (match_operand:VI4_128_8_256 0 "register_operand" "=v")
|
||||
(any_fix:VI4_128_8_256
|
||||
(vec_select:V4HF
|
||||
(match_operand:V8HF 1 "register_operand" "v")
|
||||
(parallel [(const_int 0) (const_int 1) (const_int 2) (const_int 3)]))))]
|
||||
"TARGET_AVX512FP16 && TARGET_AVX512VL"
|
||||
"vcvttph2<fixsuffix><sseintconvert>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
|
||||
[(set_attr "type" "ssecvt")
|
||||
(set_attr "prefix" "evex")
|
||||
(set_attr "mode" "<sseinsnmode>")])
|
||||
|
||||
(define_insn "*avx512fp16_fix<fixunssuffix>_trunc<mode>2_load<mask_name>"
|
||||
[(set (match_operand:VI4_128_8_256 0 "register_operand" "=v")
|
||||
(any_fix:VI4_128_8_256
|
||||
(match_operand:V4HF 1 "memory_operand" "m")))]
|
||||
"TARGET_AVX512FP16 && TARGET_AVX512VL"
|
||||
"vcvttph2<fixsuffix><sseintconvert>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %q1}"
|
||||
[(set_attr "type" "ssecvt")
|
||||
(set_attr "prefix" "evex")
|
||||
(set_attr "mode" "<sseinsnmode>")])
|
||||
|
||||
(define_insn "avx512fp16_fix<fixunssuffix>_truncv2di2<mask_name>"
|
||||
[(set (match_operand:V2DI 0 "register_operand" "=v")
|
||||
(any_fix:V2DI
|
||||
(vec_select:V2HF
|
||||
(match_operand:V8HF 1 "nonimmediate_operand" "v")
|
||||
(parallel [(const_int 0) (const_int 1)]))))]
|
||||
"TARGET_AVX512FP16 && TARGET_AVX512VL"
|
||||
"vcvttph2<fixsuffix>qq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
|
||||
[(set_attr "type" "ssecvt")
|
||||
(set_attr "prefix" "evex")
|
||||
(set_attr "mode" "TI")])
|
||||
|
||||
(define_insn "*avx512fp16_fix<fixunssuffix>_truncv2di2_load<mask_name>"
|
||||
[(set (match_operand:V2DI 0 "register_operand" "=v")
|
||||
(any_fix:V2DI
|
||||
(match_operand:V2HF 1 "memory_operand" "m")))]
|
||||
"TARGET_AVX512FP16 && TARGET_AVX512VL"
|
||||
"vcvttph2<fixsuffix>qq\t{%1, %0<mask_operand2>|%0<mask_operand2>, %k1}"
|
||||
[(set_attr "type" "ssecvt")
|
||||
(set_attr "prefix" "evex")
|
||||
(set_attr "mode" "TI")])
|
||||
|
||||
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
|
||||
;;
|
||||
;; Parallel single-precision floating point conversion operations
|
||||
|
|
|
|||
|
|
@ -723,8 +723,14 @@
|
|||
#define __builtin_ia32_vcvtph2udq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2udq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2qq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2qq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2uqq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2uqq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2dq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2dq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2udq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2udq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2qq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2qq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2uqq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2uqq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2w512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2w512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2uw512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2uw512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2w512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2w512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2uw512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2uw512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtw2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtw2ph512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtuw2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtuw2ph512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtdq2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtdq2ph512_mask_round(A, B, C, 8)
|
||||
|
|
|
|||
|
|
@ -740,8 +740,14 @@
|
|||
#define __builtin_ia32_vcvtph2udq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2udq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2qq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2qq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2uqq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2uqq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2dq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2dq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2udq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2udq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2qq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2qq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2uqq512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2uqq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2w512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2w512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2uw512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2uw512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2w512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2w512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2uw512_mask_round(A, B, C, D) __builtin_ia32_vcvttph2uw512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtw2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtw2ph512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtuw2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtuw2ph512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtdq2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtdq2ph512_mask_round(A, B, C, 8)
|
||||
|
|
|
|||
|
|
@ -680,8 +680,14 @@ test_1 (_mm512_roundscale_ph, __m512h, __m512h, 123)
|
|||
test_1 (_mm512_getexp_round_ph, __m512h, __m512h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epi16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epu16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epi16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epu16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epi32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epu32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epi32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epu32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epi64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epu64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epi64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epu64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvt_roundepi16_ph, __m512h, __m512i, 8)
|
||||
|
|
@ -732,10 +738,16 @@ test_2 (_mm512_maskz_getexp_round_ph, __m512h, __mmask32, __m512h, 8)
|
|||
test_2 (_mm_getexp_round_sh, __m128h, __m128h, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epi32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epu32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epi64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epu64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epi32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epu32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epi64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epu64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundepi16_ph, __m512h, __mmask32, __m512i, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundepu16_ph, __m512h, __mmask32, __m512i, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundepi32_ph, __m256h, __mmask16, __m512i, 8)
|
||||
|
|
@ -784,10 +796,16 @@ test_3 (_mm_maskz_getexp_round_sh, __m128h, __mmask8, __m128h, __m128h, 8)
|
|||
test_3 (_mm512_mask_getexp_round_ph, __m512h, __m512h, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epi32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epu32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epi64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epu64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epi32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epu32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epi64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epu64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundepi16_ph, __m512h, __m512h, __mmask32, __m512i, 8)
|
||||
test_3 (_mm512_mask_cvt_roundepu16_ph, __m512h, __m512h, __mmask32, __m512i, 8)
|
||||
test_3 (_mm512_mask_cvt_roundepi32_ph, __m256h, __m256h, __mmask16, __m512i, 8)
|
||||
|
|
|
|||
|
|
@ -785,10 +785,16 @@ test_1 (_mm512_roundscale_ph, __m512h, __m512h, 123)
|
|||
test_1 (_mm512_getexp_round_ph, __m512h, __m512h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epi16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epu16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epi16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epu16, __m512i, __m512h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epi32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epu32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epi64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvt_roundph_epu64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epi32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epu32, __m512i, __m256h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epi64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvtt_roundph_epu64, __m512i, __m128h, 8)
|
||||
test_1 (_mm512_cvt_roundepi16_ph, __m512h, __m512i, 8)
|
||||
test_1 (_mm512_cvt_roundepu16_ph, __m512h, __m512i, 8)
|
||||
test_1 (_mm512_cvt_roundepi32_ph, __m256h, __m512i, 8)
|
||||
|
|
@ -836,10 +842,16 @@ test_2 (_mm512_maskz_getexp_round_ph, __m512h, __mmask32, __m512h, 8)
|
|||
test_2 (_mm_getexp_round_sh, __m128h, __m128h, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epi16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epu16, __m512i, __mmask32, __m512h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epi32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epu32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epi64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundph_epu64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epi32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epu32, __m512i, __mmask16, __m256h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epi64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvtt_roundph_epu64, __m512i, __mmask8, __m128h, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundepi16_ph, __m512h, __mmask32, __m512i, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundepu16_ph, __m512h, __mmask32, __m512i, 8)
|
||||
test_2 (_mm512_maskz_cvt_roundepi32_ph, __m256h, __mmask16, __m512i, 8)
|
||||
|
|
@ -887,10 +899,16 @@ test_3 (_mm_maskz_getexp_round_sh, __m128h, __mmask8, __m128h, __m128h, 8)
|
|||
test_3 (_mm512_mask_getexp_round_ph, __m512h, __m512h, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epi16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epu16, __m512i, __m512i, __mmask32, __m512h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epi32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epu32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epi64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundph_epu64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epi32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epu32, __m512i, __m512i, __mmask16, __m256h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epi64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvtt_roundph_epu64, __m512i, __m512i, __mmask8, __m128h, 8)
|
||||
test_3 (_mm512_mask_cvt_roundepi16_ph, __m512h, __m512h, __mmask32, __m512i, 8)
|
||||
test_3 (_mm512_mask_cvt_roundepu16_ph, __m512h, __m512h, __mmask32, __m512i, 8)
|
||||
test_3 (_mm512_mask_cvt_roundepi32_ph, __m256h, __m256h, __mmask16, __m512i, 8)
|
||||
|
|
|
|||
|
|
@ -741,8 +741,14 @@
|
|||
#define __builtin_ia32_vcvtph2udq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2udq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2qq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2qq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2uqq512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2uqq512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2dq_v16si_mask_round(A, B, C, D) __builtin_ia32_vcvttph2dq_v16si_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2udq_v16si_mask_round(A, B, C, D) __builtin_ia32_vcvttph2udq_v16si_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2qq_v8di_mask_round(A, B, C, D) __builtin_ia32_vcvttph2qq_v8di_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2uqq_v8di_mask_round(A, B, C, D) __builtin_ia32_vcvttph2uqq_v8di_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2w512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2w512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtph2uw512_mask_round(A, B, C, D) __builtin_ia32_vcvtph2uw512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2w_v32hi_mask_round(A, B, C, D) __builtin_ia32_vcvttph2w_v32hi_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvttph2uw_v32hi_mask_round(A, B, C, D) __builtin_ia32_vcvttph2uw_v32hi_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtw2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtw2ph512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtuw2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtuw2ph512_mask_round(A, B, C, 8)
|
||||
#define __builtin_ia32_vcvtdq2ph512_mask_round(A, B, C, D) __builtin_ia32_vcvtdq2ph512_mask_round(A, B, C, 8)
|
||||
|
|
|
|||
Loading…
Reference in New Issue